20 citations · 43 across the 19 of their papers we have counts for
19 papers
Trojans in Artificial Intelligence (TrojAI) Final Report
Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski +68
The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI T…
Discovering strategies for coastal resilience with AI-based prediction and optimization
Jared Markowitz, Alexander New, Jennifer Sleeman +5
Tropical storms cause extensive property damage and loss of life, making them one of the most destructive types of natural hazards. The development of predictive models that identi…
Large Language Models are Highly Aligned with Human Ratings of Emotional Stimuli
Mattson Ogg, Chace Ashcraft, Ritwik Bose +2
Emotions exert an immense influence over human behavior and cognition in both commonplace and high-stress tasks. Discussions of whether or how to integrate large language models (L…
Backdoors in DRL: Four Environments Focusing on In-distribution Triggers
Chace Ashcraft, Ted Staley, Josh Carney +4
Backdoor attacks, or trojans, pose a security risk by concealing undesirable behavior in deep neural network models. Open-source neural networks are downloaded from the internet da…
Investigating the Treacherous Turn in Deep Reinforcement Learning
Chace Ashcraft, Kiran Karra, Josh Carney +1
The Treacherous Turn refers to the scenario where an artificial intelligence (AI) agent subtly, and perhaps covertly, learns to perform a behavior that benefits itself but is deeme…
Difference Learning for Air Quality Forecasting Transport Emulation
Reed River Chen, Christopher Ribaudo, Jennifer Sleeman +6
Human health is negatively impacted by poor air quality including increased risk for respiratory and cardiovascular disease. Due to a recent increase in extreme air quality events,…
Neuro-Symbolic Bi-Directional Translation -- Deep Learning Explainability for Climate Tipping Point Research
Chace Ashcraft, Jennifer Sleeman, Caroline Tang +2
In recent years, there has been an increase in using deep learning for climate and weather modeling. Though results have been impressive, explainability and interpretability of dee…
A Generative Adversarial Network for Climate Tipping Point Discovery (TIP-GAN)
Jennifer Sleeman, David Chung, Anand Gnanadesikan +10
We propose a new Tipping Point Generative Adversarial Network (TIP-GAN) for better characterizing potential climate tipping points in Earth system models. We describe an adversaria…
Using Artificial Intelligence to aid Scientific Discovery of Climate Tipping Points
Jennifer Sleeman, David Chung, Chace Ashcraft +10
We propose a hybrid Artificial Intelligence (AI) climate modeling approach that enables climate modelers in scientific discovery using a climate-targeted simulation methodology bas…
Context-Adaptive Deep Neural Networks via Bridge-Mode Connectivity
Nathan Drenkow, Alvin Tan, Chace Ashcraft +1
The deployment of machine learning models in safety-critical applications comes with the expectation that such models will perform well over a range of contexts (e.g., a vision mod…
Latent Properties of Lifelong Learning Systems
Corban Rivera, Chace Ashcraft, Alexander New +2
Creating artificial intelligence (AI) systems capable of demonstrating lifelong learning is a fundamental challenge, and many approaches and metrics have been proposed to analyze a…
Structural Similarity for Improved Transfer in Reinforcement Learning
C. Chace Ashcraft, Benjamin Stoler, Chigozie Ewulum +1
Transfer learning is an increasingly common approach for developing performant RL agents. However, it is not well understood how to define the relationship between the source and t…
L2Explorer: A Lifelong Reinforcement Learning Assessment Environment
Erik C. Johnson, Eric Q. Nguyen, Blake Schreurs +6
Despite groundbreaking progress in reinforcement learning for robotics, gameplay, and other complex domains, major challenges remain in applying reinforcement learning to the evolv…
Meta Arcade: A Configurable Environment Suite for Meta-Learning
Edward W. Staley, Chace Ashcraft, Benjamin Stoler +4
Most approaches to deep reinforcement learning (DRL) attempt to solve a single task at a time. As a result, most existing research benchmarks consist of individual games or suites…
Machine Learning aided Crop Yield Optimization
Chace Ashcraft, Kiran Karra
We present a crop simulation environment with an OpenAI Gym interface, and apply modern deep reinforcement learning (DRL) algorithms to optimize yield. We empirically show that DRL…
SanitAIs: Unsupervised Data Augmentation to Sanitize Trojaned Neural Networks
Kiran Karra, Chace Ashcraft, Cash Costello
Self-supervised learning (SSL) methods have resulted in broad improvements to neural network performance by leveraging large, untapped collections of unlabeled data to learn genera…
Poisoning Deep Reinforcement Learning Agents with In-Distribution Triggers
Chace Ashcraft, Kiran Karra
In this paper, we propose a new data poisoning attack and apply it to deep reinforcement learning agents. Our attack centers on what we call in-distribution triggers, which are tri…
PICO: Primitive Imitation for COntrol
Corban G. Rivera, Katie M. Popek, Chace Ashcraft +3
In this work, we explore a novel framework for control of complex systems called Primitive Imitation for Control PICO. The approach combines ideas from imitation learning, task dec…
The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models
Kiran Karra, Chace Ashcraft, Neil Fendley
In this paper, we introduce the TrojAI software framework, an open source set of Python tools capable of generating triggered (poisoned) datasets and associated deep learning (DL)…